{"id":"https://openalex.org/W2161727827","doi":"https://doi.org/10.1109/tasl.2010.2041113","title":"Evaluation of Expressive Speech Synthesis With Voice Conversion and Copy Resynthesis Techniques","display_name":"Evaluation of Expressive Speech Synthesis With Voice Conversion and Copy Resynthesis Techniques","publication_year":2010,"publication_date":"2010-04-09","ids":{"openalex":"https://openalex.org/W2161727827","doi":"https://doi.org/10.1109/tasl.2010.2041113","mag":"2161727827"},"language":"en","primary_location":{"id":"doi:10.1109/tasl.2010.2041113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2041113","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5046810738","display_name":"Oytun T\u00fcrk","orcid":null},"institutions":[{"id":"https://openalex.org/I4210111469","display_name":"Sensory Cloud (United States)","ror":"https://ror.org/01vny5262","country_code":"US","type":"company","lineage":["https://openalex.org/I4210111469"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Oytun Turk","raw_affiliation_strings":["Sensory, Inc., Portland, OR, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sensory, Inc., Portland, OR, USA","institution_ids":["https://openalex.org/I4210111469"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110281069","display_name":"Marc L. Schr\u00f6der","orcid":null},"institutions":[{"id":"https://openalex.org/I33256026","display_name":"German Research Centre for Artificial Intelligence","ror":"https://ror.org/01ayc5b57","country_code":"DE","type":"funder","lineage":["https://openalex.org/I33256026"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marc Schroder","raw_affiliation_strings":["Speech Group, DFKI GmbH Language Technology Laboratory, Saarbrucken, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Speech Group, DFKI GmbH Language Technology Laboratory, Saarbrucken, Germany","institution_ids":["https://openalex.org/I33256026"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.263,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.92697417,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"18","issue":"5","first_page":"965","last_page":"973"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9955999851226807,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/naturalness","display_name":"Naturalness","score":0.9118361473083496},{"id":"https://openalex.org/keywords/prosody","display_name":"Prosody","score":0.8279858827590942},{"id":"https://openalex.org/keywords/speech-synthesis","display_name":"Speech synthesis","score":0.7731789350509644},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7252653241157532},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.7141261696815491},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.5191820859909058},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.5162851214408875},{"id":"https://openalex.org/keywords/vocal-tract","display_name":"Vocal tract","score":0.4572018086910248},{"id":"https://openalex.org/keywords/active-listening","display_name":"Active listening","score":0.4135759174823761},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.38860487937927246},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.14643940329551697},{"id":"https://openalex.org/keywords/communication","display_name":"Communication","score":0.1349441409111023}],"concepts":[{"id":"https://openalex.org/C134537474","wikidata":"https://www.wikidata.org/wiki/Q17144832","display_name":"Naturalness","level":2,"score":0.9118361473083496},{"id":"https://openalex.org/C542774811","wikidata":"https://www.wikidata.org/wiki/Q10880526","display_name":"Prosody","level":2,"score":0.8279858827590942},{"id":"https://openalex.org/C14999030","wikidata":"https://www.wikidata.org/wiki/Q16346","display_name":"Speech synthesis","level":2,"score":0.7731789350509644},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7252653241157532},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.7141261696815491},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.5191820859909058},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.5162851214408875},{"id":"https://openalex.org/C47401133","wikidata":"https://www.wikidata.org/wiki/Q748953","display_name":"Vocal tract","level":2,"score":0.4572018086910248},{"id":"https://openalex.org/C177291462","wikidata":"https://www.wikidata.org/wiki/Q423038","display_name":"Active listening","level":2,"score":0.4135759174823761},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.38860487937927246},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.14643940329551697},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.1349441409111023},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C59822182","wikidata":"https://www.wikidata.org/wiki/Q441","display_name":"Botany","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tasl.2010.2041113","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tasl.2010.2041113","pdf_url":null,"source":{"id":"https://openalex.org/S199497470","display_name":"IEEE Transactions on Audio Speech and Language Processing","issn_l":"1558-7916","issn":["1558-7916","1558-7924"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Audio, Speech, and Language Processing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":56,"referenced_works":["https://openalex.org/W51255321","https://openalex.org/W54773229","https://openalex.org/W75704375","https://openalex.org/W76953495","https://openalex.org/W84898526","https://openalex.org/W95551363","https://openalex.org/W153299664","https://openalex.org/W161490846","https://openalex.org/W170974841","https://openalex.org/W175750906","https://openalex.org/W190419602","https://openalex.org/W198298781","https://openalex.org/W204428907","https://openalex.org/W226412370","https://openalex.org/W272162490","https://openalex.org/W1496562625","https://openalex.org/W1572730534","https://openalex.org/W1588037970","https://openalex.org/W1592940279","https://openalex.org/W1600722501","https://openalex.org/W1854508109","https://openalex.org/W1870008521","https://openalex.org/W1892640180","https://openalex.org/W1970863292","https://openalex.org/W1991402032","https://openalex.org/W2009226274","https://openalex.org/W2009417200","https://openalex.org/W2033641795","https://openalex.org/W2067234399","https://openalex.org/W2101053356","https://openalex.org/W2107541077","https://openalex.org/W2118850452","https://openalex.org/W2119929864","https://openalex.org/W2123003832","https://openalex.org/W2126143605","https://openalex.org/W2146927751","https://openalex.org/W2148846882","https://openalex.org/W2156060621","https://openalex.org/W2156142001","https://openalex.org/W2160379050","https://openalex.org/W2160464533","https://openalex.org/W2161855744","https://openalex.org/W2188791853","https://openalex.org/W2244925781","https://openalex.org/W2534570126","https://openalex.org/W3130240200","https://openalex.org/W4252684946","https://openalex.org/W4301420498","https://openalex.org/W6606963762","https://openalex.org/W6608022165","https://openalex.org/W6608969598","https://openalex.org/W6638813705","https://openalex.org/W6683927816","https://openalex.org/W6683973074","https://openalex.org/W6865107258","https://openalex.org/W7024953085"],"related_works":["https://openalex.org/W169399214","https://openalex.org/W3100825170","https://openalex.org/W1914543332","https://openalex.org/W1984347656","https://openalex.org/W2946856121","https://openalex.org/W10581632","https://openalex.org/W2020989338","https://openalex.org/W1927421023","https://openalex.org/W2108985546","https://openalex.org/W2433276473"],"abstract_inverted_index":{"Generating":[0],"expressive":[1,13,107,145],"synthetic":[2,122],"voices":[3],"requires":[4],"carefully":[5],"designed":[6],"databases":[7],"that":[8,152],"contain":[9],"sufficient":[10],"amount":[11,55],"of":[12,46,56,131,163,178,185],"speech":[14,108,123],"material.":[15],"This":[16],"paper":[17],"investigates":[18],"voice":[19,47,82,132,165,187],"conversion":[20],"and":[21,28,35,49,73,134,147,159,167,189],"modification":[22],"techniques":[23],"to":[24,119,170,199,205],"reduce":[25],"database":[26],"collection":[27],"processing":[29],"efforts":[30],"while":[31],"maintaining":[32],"acceptable":[33],"quality":[34,48,83,133,166,188],"naturalness.":[36,160],"In":[37],"a":[38,113,155,200],"factorial":[39],"design,":[40],"we":[41],"study":[42],"the":[43,54,60,171,176,194,206],"relative":[44],"contributions":[45],"prosody":[50,101,135,168],"as":[51,53,112,191,203],"well":[52],"distortions":[57],"introduced":[58],"by":[59,193],"respective":[61],"signal":[62],"manipulation":[63],"steps.":[64],"The":[65,105,149,182],"unit":[66],"selection":[67],"engine":[68],"in":[69,140],"our":[70],"open":[71],"source":[72],"modular":[74],"text-to-speech":[75],"(TTS)":[76],"framework":[77],"MARY":[78],"is":[79,154],"extended":[80],"with":[81,99],"transformation":[84,136],"using":[85],"either":[86],"GMM-based":[87],"prediction":[88],"or":[89,127],"vocal":[90],"tract":[91],"copy":[92,102,195],"resynthesis.":[93],"These":[94],"algorithms":[95,137],"are":[96,138],"then":[97],"cross-combined":[98],"various":[100],"resynthesis":[103],"methods.":[104],"overall":[106],"generation":[109],"process":[110],"functions":[111],"postprocessing":[114],"step":[115],"on":[116],"TTS":[117],"outputs":[118],"transform":[120],"neutral":[121],"into":[124],"aggressive,":[125],"cheerful,":[126],"depressed":[128],"speech.":[129],"Cross-combinations":[130],"compared":[139,204],"listening":[141],"tests":[142],"for":[143],"perceived":[144],"style":[146],"quality.":[148],"results":[150],"show":[151],"there":[153],"tradeoff":[156],"between":[157],"identification":[158,173,202],"Combined":[161],"modeling":[162],"both":[164,186],"leads":[169],"best":[172],"scores":[174],"at":[175],"expense":[177],"lowest":[179],"naturalness":[180],"ratings.":[181],"fine":[183],"detail":[184],"prosody,":[190],"preserved":[192],"synthesis,":[196],"did":[197],"contribute":[198],"better":[201],"approximate":[207],"models.":[208]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}